© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50862
    Prev
    Next
    INDEX
    Explanations

    cycling events and competitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SPELL
    -0.10
    俵
    -0.09
    è´Ŀ壳
    -0.09
    Spell
    -0.09
    roperty
    -0.09
    ombo
    -0.08
     rept
    -0.08
    åŁķ
    -0.08
    çıŃ主任
    -0.08
    LEAR
    -0.08
    POSITIVE LOGITS
    éªijè¡Į
    0.19
    èĩªè¡Į车
    0.16
     bike
    0.13
    æij©æīĺ车
    0.13
     cyclists
    0.12
    bike
    0.12
     cyclist
    0.12
    éªij
    0.11
    åįķ车
    0.11
    åħ±äº«åįķ车
    0.11
    Activations Density 0.158%

    No Known Activations